Delete one or more emails by moving to Trash, or permanently destroy them.
AI agents call mail_delete_email to permanently remove resources in Pyfastmail — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Permanent destruction of emails cannot be undone and represents irreversible data loss. Even though the tool offers a reversible path (moving to Trash), the permanent destroy capability qualifies this as Destructive rather than Write.
From the tool's definition Tool description states 'permanently destroy them' — this explicitly indicates irreversible deletion of email data. The name 'mail_delete_email' combined with the capability to 'permanently destroy' emails confirms destructive intent.
Attacks that exploit this kind of access
Delete one or more emails by moving to Trash, or permanently destroy them. It is categorised as a Destructive tool in the Pyfastmail MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Pyfastmail MCP server in PolicyLayer and add a rule for mail_delete_email: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Pyfastmail. Nothing to install.
mail_delete_email is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the mail_delete_email rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for mail_delete_email. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
mail_delete_email is provided by the Pyfastmail MCP server (pjosols/pyfastmail-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →